INDEX

Explanations

words associated with temperature and design

warm

New Auto-Interp

Configuration

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

Negative Logits

 warm

-3.00

 Warm

-2.92

Warm

-2.88

warm

-2.70

 WARM

-2.59

 warmed

-2.36

 warms

-2.34

 warmer

-2.30

WARM

-2.28

 warmth

-2.27

POSITIVE LOGITS

Blas

0.49

 Blas

0.48

veras

0.45

ByExample

0.44

ritus

0.44

Toole

0.43

Risultati

0.43

rej

0.42

 χρη

0.41

Minn

0.41

Activations Density 1.572%